© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5735
    Prev
    Next
    INDEX
    Explanations

    reverse, opposite, other way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    翼
    -0.09
    _PF
    -0.09
    /goto
    -0.09
    æīĢåľ¨çļĦ
    -0.09
    vant
    -0.09
    æľīæķĪæĢ§
    -0.09
    娣
    -0.09
    зам
    -0.08
    ahoo
    -0.08
     Eg
    -0.08
    POSITIVE LOGITS
    缸åıį
    0.35
    åıįä¹ĭ
    0.29
    åıįè¿ĩæĿ¥
    0.29
     opposite
    0.26
     reverse
    0.23
     vice
    0.23
    vice
    0.20
    reverse
    0.19
    .reverse
    0.19
    Reverse
    0.19
    Activations Density 0.052%

    No Known Activations